emirdemirel / alta Goto Github PK
View Code? Open in Web Editor NEWA complete training recipe for kaldi-based Automatic Lyrics Transcription.
License: Other
A complete training recipe for kaldi-based Automatic Lyrics Transcription.
License: Other
`(base) [wxk@localhost s5]$ sh run_damp.sh
===> START TIME : 03/05/21_10:29:02 =====
==================
----- Training Neural Networks for the Acoustic Model -----
===== 03/05/21_10:29:02 =====
local/chain/run_ctdnn_sa.sh --stage 3 --train_stage -10 train dev test
local/chain/run_ctdnn_sa.sh: expected file exp/tri3b/final.mdl to exist`
Hi! I am preparing the data but found some audio files are not available owing to copyright issue with DALI dataset. How do you suggest to solve this problem to fairly compare the transcription results? Thanks!
Hi there,
I submitted an authorization request to access the DSing!300x30x2 dataset at the beginning of May. Just curious if requests for this dataset are still being approved. Please let me know.
ALTA/s5/local/chain/run_ctdnn_sa.sh
Line 118 in fcbb838
ALTA/s5/local/chain/run_ctdnn_sa.sh
Line 128 in fcbb838
ALTA/s5/local/chain/run_ctdnn_sa.sh
Line 175 in fcbb838
Just recently attempted to build the project without success.
below is the error message.
and suggestions are appreciated.
Cheers
-D
../../Repos\ALTA> docker build --tag alta:latest -f Dockerfile .
docker : #1 [internal] load build definition from Dockerfile
At line:1 char:1
+ CategoryInfo : NotSpecified: (#1 [internal] l...from Dockerfile:String) [], RemoteException
+ FullyQualifiedErrorId : NativeCommandError
#1 sha256:09f737f45212a436ca10877af5e59da641d6e2a7dbd7f45124fa22866d732c24
#1 transferring dockerfile: 32B 0.0s done
#1 DONE 0.0s
#2 [internal] load .dockerignore
#2 sha256:3d7720e194411ef67e1bc0f2beea870bdee91e5cd24649799c6e2d4136bc878f
#2 transferring context: 2B 0.0s done
#2 DONE 0.0s
failed to solve with frontend dockerfile.v0: failed to create LLB definition: dockerfile parse error line 58:
unknown instruction: FIND
Wonderful/proper work!
Any support for simple Windows + Python IDE usage?
ALTA/s5/local/chain/run_ctdnn_sa.sh
Lines 173 to 176 in fcbb838
Console log:
train
local/nnet3/run_alignment_gmm_sp.sh --stage 10 --nj 30 --train_set train --test_sets dev test --gmm_dir exp/tri3b --ali_dir exp/tri3b_ali_train_sp --lat_dir exp/chain_cleaned/tri3b_train_sp_lats
local/nnet3/run_alignment_gmm_sp.sh: aligning with the perturbed low-resolution data
steps/align_fmllr.sh --nj 30 --cmd run.pl --max-jobs-run 3 --beam 40 --retry_beam 500 data/train_sp data/lang
usage: steps/align_fmllr.sh
e.g.: steps/align_fmllr.sh data/train data/lang exp/tri1 exp/tri1_ali
main options (for others, see top of script file)
--config # config containing options
--nj # number of parallel jobs
--use-graphs true # use graphs in src-dir
--cmd (utils/run.pl|utils/queue.pl ) # how to run jobs.
--fmllr-update-type (full|diag|offset|none) # default full.
----- Training Neural Networks for the Acoustic Model -----
local/chain/run_ctdnn_sa.sh --stage 3 --train_stage -10 train dev test
--- i-Vector Training - for singer adaptive NN training ---
local/nnet3/run_ivector_training.sh --stage 0 --nj 30 --train_set train
local/nnet3/run_ivector_training.sh: computing a subset of data to train the diagonal UBM.
local/nnet3/run_ivector_training.sh: line 32: data/train_sp_hires/utt2spk: No such file or directory
I have run all stages until stage 6
When i run ./run_damp.sh $damp_data
i get the above message. In which stage was the folder train_sp_hires
created?
oops just delete
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.